LRN

Description

Normalizes the local response of the input tensor.

Input

One input:

x: tensor of type float16 or float.

Output

One output:

y: tensor of the identical data type and format as input x.

Property

alpha: float, scaling factor.

beta: float, exponent.

bias: float, an optional float32. Offset. Generally, the value is greater than 0 to avoid dividing by 0.

size: int, number of channels to be summed. Only an odd number is supported.

ONNX Opset Support

Opset v8/v9/v10/v11/v12/v13/v14/v15/v16/v17/v18